© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 8220
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing clarity and precision in communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.01
    2:0.09
    3:0.05
    4:0.10
    5:0.03
    6:0.04
    7:0.43
    8:0.02
    9:0.03
    10:0.06
    11:0.06
    Negative Logits
     Rou
    -1.52
     airs
    -1.42
    mon
    -1.41
    ortun
    -1.36
    unia
    -1.30
     Horses
    -1.29
    ा
    -1.29
     Democracy
    -1.28
     monop
    -1.27
     Tud
    -1.27
    POSITIVE LOGITS
     unlaw
    1.92
     unamb
    1.87
     unequiv
    1.80
    furt
    1.57
    iguous
    1.54
     boundaries
    1.52
    isphere
    1.50
    codes
    1.48
    insula
    1.46
    btn
    1.44
    Activations Density 0.037%

    No Known Activations